This paper investigates a stopping rule to be utilised in phase I clinical trials. The motivation is to develop a dynamic rule so that a trial stops early if the maximum tolerated dose lies towards the beginning of a dose region. Also, it will employ many patients if the maximum tolerated dose lies towards the end of a dose region. A two-parameter logistic model is assumed for the dose-response data. A trial is stopped early before reaching the maximum number of patients when the width of the Bayesian posterior probability interval of the slope parameter meets a desired value. Instead of setting a pre-specified width to stop at, we determine it based on the parameter estimate obtained after a reasonable number of steps in a trial. Simulation studies of six plausible dose-response scenarios show that the proposed stopping rule is capable of limiting the number of patients to be recruited depending on the underlying scenario. Although the rule is applied to a D-optimum design here, it will be equally applicable to other model-based designs.
Alam M.I. (2016): A comparison between the continual reassessment method and D-optimum design for dose finding in phase I clinical trials. Biometrical Letters 53(2): 69-82.
Atkinson A.C., Fedorov V.V., Herzberg A.M., Zhang R. (2014): Elemental information matrices and optimal experimental design for generalized regression models. Journal of Statistical Planning and Inference 144(1): 81-91.
Brunier H.C., Whitehead J. (1994): Sample sizes for phase II clinical trials derived from Bayesian decision theory. Statistics in Medicine 13(23-24): 2493-2502.
Chernoff H. (1953): Locally optimal designs for estimating parameters. The Annals of Mathematical Statistics 24(4): 586-602.
Heyd J.M., Carlin B.P. (1999): Adaptive design improvements in the continual reassessment method for phase I studies. Statistics in Medicine 18(11): 1307-1321.
Korn E.L., Midthune D., Chen T.T, Rubinstein L.V., Christian M.C., Simon R.M. (1994): A comparison of two phase I trial designs. Statistics in Medicine 13(18): 1799-1806.
O’Quigley J. (2002): Continual reassessment designs with early termination. Biostatistics 3(1): 87-99.
O’Quigley J., Reiner E. (1998): A stopping rule for the continual reassessment method. Biometrika 85(3): 741-748.
Stallard N. (1998): Sample size determination for phase II clinical trials based on Bayesian decision theory. Biometrics 54(1): 279-294.
Thall P.F., Russell K.E. (1998): A strategy for dose-finding and safety monitoring based on efficacy and adverse outcomes in phase I/II clinical trials. Biometrics 54(1): 251-264.
Tighiouart M., Rogatko A. (2012): Number of patients per cohort and sample size considerations using dose escalation with overdose control. Journal of Probability and Statistics 2012: Article ID 692725, pp. 16, doi:
Zohar S., Chevret S. (2001): The continual reassessment method: comparison of Bayesian stopping rules for dose-ranging studies. Statistics in Medicine 20(19): 2827-2843.
Zohar S., Latouche A., Taconnet M., Chevret S. (2003): Software to compute and conduct sequential bayesian phase I or II dose-ranging clinical trials with stopping rules. Computer Methods and Programs in Biomedicine 72(2): 117-125.